mcp · handle luda
mcp_vnc · job 77%nuphus_mcp · job 79%open_codex_computer_use · job 78%glasswarp_mcp_server · job 74%Hyprland MCP · job 75%touchpoint · job 78%gnome_mcp_server · job 74%Guarded Computer Use MCP · job 76%computer-control · job 79%screenhand · job 75%swift_mcp_gui · job 77%computer_use_mcp · job 78%agentfenster · job 75%hypr_cua_mcp · job 73%desktop-hub · job 73%Mint Computer MCP · job 80%Desktop Automation MCP · job 75%Sideyard · job 81%DSH Computer Use · job 76%Rênes · job 73%ControlFreak · job 74%ChatGPT Desktop MCP · job 74%OpenSky · job 78%clawdcursor · job 76%plonk_2 · job 75%Computer Use MCP · job 80%MCP Computer Use · job 81%aos · job 82%Sloth MCP · job 75%UltraNix MCP · job 82%Computer Use · job 74%kasm-use · job 76%PcGöz · job 74%Tiance GUI MCP · job 78%mcp_pyautogui · job 81%kwin_mcp · job 75%rdc · job 80%hypruse · job 77%use-computer · job 76%uitap · job 78%mcp-winaccess-win · job 79%computer-use-linux · job 89%OpenComputerUse · job 75%Claude Background Control · job 73%AiPC · job 80%Auten · job 75%cc-computer-use · job 83%zcode-desktop-control · job 74%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series